Research map / Label-efficient and robust learning / Recognition and long-tail
Integrating Relation Constraints with Neural Relation Extractors
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add Coherent Constraint Loss | ACNN · English dataset | Mean P@N (%): 93.68 -> 93.96 | Helped |
| Add Semantic Constraint Loss | ACNN · English dataset | Mean P@N (%): 93.68 -> 95.87 | Helped |
| Add Coherent Constraint Loss | APCNN · English dataset | Mean P@N (%): 98.79 -> 98.97 | Helped |
| Add Semantic Constraint Loss | APCNN · English dataset | Mean P@N (%): 98.79 -> 99.32 | Helped |
| Add Coherent Constraint Loss | ACNN · Chinese dataset | Mean P@N (%): 86.83 -> 94.59 | Helped |
| Add Semantic Constraint Loss | ACNN · Chinese dataset | Mean P@N (%): 86.83 -> 94.70 | Helped |
| Add Coherent Constraint Loss | APCNN · Chinese dataset | Mean P@N (%): 91.93 -> 96.62 | Helped |
| Add Semantic Constraint Loss | APCNN · Chinese dataset | Mean P@N (%): 91.93 -> 96.80 | Helped |
| Use Semantic rather than Coherent constraint loss (ablation) | APCNN · Chinese dataset | Mean P@N (%): 96.62 -> 96.80 | Helped |
| Add ILP post-processing (ablation) | ACNN(Sem) · English dataset | Mean P@N (%): 95.87 -> 96.75 | Helped |
| Add ILP post-processing (ablation) | APCNN(Sem) · Chinese dataset | Mean P@N (%): 96.80 -> 97.31 | Helped |
| Use dynamic rather than constant constraint-loss coefficient (ablation) | APCNN · English dataset | Mean P@N (%): 99.32% -> 99.33% | No clear effect |
Closest papers by meaning
- SEE: Syntax-Aware Entity Embedding for Neural Relation Extraction (AAAI 2018 · similarity 0.88)
- Neural Relation Extraction within and across Sentence Boundaries (AAAI 2019 · similarity 0.88)
- Joint Entity and Relation Extraction with a Hybrid Transformer and Reinforcement Learning Based Model (AAAI 2020 · similarity 0.87)
- Communicative Message Passing for Inductive Relation Reasoning (AAAI 2021 · similarity 0.87)
- Distilling Knowledge from Well-Informed Soft Labels for Neural Relation Extraction (AAAI 2020 · similarity 0.87)
- Enhancing Low-Resource Relation Representations through Multi-View Decoupling (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.